Claude Opus 4.6 (Non-reasoning, High Effort)
Intelligence
46.5
#46/523
Coding
47.6
#18/429
Math
—
Speed
45 tok/s
TTFT: 2.01s
Pricing
$5.00 / $25.00
per 1M tokens (in/out)
Claude Opus 4.6 (Non-reasoning, High Effort) is Anthropic’s latest model designed for complex tasks requiring high effort. It processes at 45.364 tokens per second and is priced at $5 per million input tokens and $25 per million output tokens, targeting professional users.
When to Use Claude Opus 4.6 (Non-reasoning, High Effort)
✓ Best For
- Complex data analysis tasks.
- High-effort coding projects.
- Mathematical problem-solving.
✗ Not Ideal For
- Real-time reasoning applications.
- Basic conversational tasks.
How Claude Opus 4.6 (Non-reasoning, High Effort) Compares
Intelligence Index · Higher is better
OpenAIDeepSeekAnthropicGoogle
Benchmark Profile
Coding Index
AnthropicMetaDeepSeek
Output Speed · tok/s
XiaomiNVIDIAAnthropicNous Research
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (35)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 46.5 | |
| Coding Index | 47.6 | |
| GPQA | 84% | |
| HLE | 186% | |
| SWE-Bench Verified | 80.8% | |
| SciCode | 45.7% | |
| IFBench | 44.6% | |
| LCR | 58.3% | |
| TerminalBench Hard | 48.5% | |
| Tau2 | 84.8% | |
| AIME 2025 | 99.8% | |
| ARC-AGI v2 | 68.8% | |
| BrowseComp | 84% | |
| CharXiv-R | 77.4% | |
| CyberGym | 66.6% | |
| DeepSearchQA | 91.3% | |
| FigQA | 78.3% | |
| Finance Agent | 60.7% | |
| GDPval-AA | 1606% | |
| Graphwalks BFS >128k | 61.5% | |
| Graphwalks parents >128k | 95.4% | |
| Humanity's Last Exam | 53.1% | |
| MCP Atlas | 59.5% | |
| MMMLU | 91.1% | |
| MMMU-Pro | 77.3% | |
| MRCR v2 (8-needle) | 93% | |
| OpenRCA | 34.9% | |
| OSWorld | 72.7% | |
| SWE-bench Multilingual | 77.8% | |
| Tau2 Retail | 91.9% | |
| Tau2 Telecom | 99.3% | |
| Terminal-Bench 2.0 | 65.4% | |
| Vending-Bench 2 | 8017.6% | |
| Arena Chat | 14.9 | |
| Arena Coding | 21.3 |
Data: Artificial Analysis · Updated: April 10, 2026
Frequently Asked Questions (15)
When was Claude Opus 4.6 (Non-reasoning, High Effort) released?
Claude Opus 4.6 (Non-reasoning, High Effort) was released on February 5, 2026.
Who created Claude Opus 4.6 (Non-reasoning, High Effort)?
Claude Opus 4.6 (Non-reasoning, High Effort) was created by Anthropic.
How intelligent is Claude Opus 4.6 (Non-reasoning, High Effort)?
Claude Opus 4.6 (Non-reasoning, High Effort) scores 46 on the Artificial Analysis Intelligence Index, placing it well above average among other non-reasoning models in a similar price tier (median: 22).
How fast is Claude Opus 4.6 (Non-reasoning, High Effort)?
Claude Opus 4.6 (Non-reasoning, High Effort) generates output at 40.9 tokens per second (based on Anthropic's API), which is at the lower end compared to other non-reasoning models in a similar price tier (median: 56.6 t/s).
What is the latency of Claude Opus 4.6 (Non-reasoning, High Effort)?
Claude Opus 4.6 (Non-reasoning, High Effort) has a time to first token (TTFT) of 1.80s (based on Anthropic's API), which is somewhat higher than average compared to other non-reasoning models in a similar price tier (median: 1.56s).
How much does Claude Opus 4.6 (Non-reasoning, High Effort) cost?
Claude Opus 4.6 (Non-reasoning, High Effort) costs $5.00 per 1M input tokens (at the higher end, median: $2.00) and $25.00 per 1M output tokens (at the higher end, median: $8.00), based on Anthropic's API.
What is Claude Opus 4.6 (Non-reasoning, High Effort) API pricing?
Claude Opus 4.6 (Non-reasoning, High Effort) costs $5.00 per 1M input tokens and $25.00 per 1M output tokens (based on Anthropic's API). For a blended rate (3:1 input to output ratio), this is $10.00 per 1M tokens. Pricing may vary by provider.
How verbose is Claude Opus 4.6 (Non-reasoning, High Effort)?
When evaluated on the Intelligence Index, Claude Opus 4.6 (Non-reasoning, High Effort) generated 11M output tokens, which is somewhat higher than average compared to other non-reasoning models in a similar price tier (median: 6.0M).
Is Claude Opus 4.6 (Non-reasoning, High Effort) a reasoning model?
No, Claude Opus 4.6 (Non-reasoning, High Effort) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
What input modalities does Claude Opus 4.6 (Non-reasoning, High Effort) support?
Claude Opus 4.6 (Non-reasoning, High Effort) supports text and image input.
What output modalities does Claude Opus 4.6 (Non-reasoning, High Effort) support?
Claude Opus 4.6 (Non-reasoning, High Effort) supports text output.
Can Claude Opus 4.6 (Non-reasoning, High Effort) process images?
Yes, Claude Opus 4.6 (Non-reasoning, High Effort) supports image input and can analyze, describe, and answer questions about images.
Is Claude Opus 4.6 (Non-reasoning, High Effort) multimodal?
Yes, Claude Opus 4.6 (Non-reasoning, High Effort) is multimodal. It can process text and image input and generate text output.
What is the context window of Claude Opus 4.6 (Non-reasoning, High Effort)?
Claude Opus 4.6 (Non-reasoning, High Effort) has a context window of 1.0M tokens. This determines how much text and conversation history the model can process in a single request.
Is Claude Opus 4.6 (Non-reasoning, High Effort) open source?
No, Claude Opus 4.6 (Non-reasoning, High Effort) is proprietary. The model weights are not publicly available.
